Jiahao Li

Jiahao Li

Auto-generated profile, based on publicly available information

Jiahao Li

College of Electrical and Control Engineering, Xian University of Science and Technology, Xian, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 October 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
Shuai HaoShuai Hao
Shuai Hao
JLJiahao Li
Jiahao Li
XSXizi Sun
Xizi Sun
XMXu Ma
Xu Ma
BABeiyi An
Beiyi An
THTIAN HE
TIAN HE
To address the problem of traditional pedestrian detection methods being subject to random interference from the external environment and insufficient utilization of pedestrian feature information, a novel multi-modal pedestrian detection network called MDFOaNet is proposed. The proposed detection network consists of two key components: a marine predator-based multi-scale image fusion module and a pedestrian detection module with an enhanced target visual accuracy attention model. In the fusion module, a contrast-based layered enhancement method for infrared images and a sharpness-based enhancement method for visible images are proposed for the problem of blurred pedestrian features in images. Moreover, to control the trade-off between fusion sub-layers, a dynamic image reconstruction model that relies on adaptive optimization based on marine predators is designed. Meanwhile, in the pedestrian detection module, to pay more attention to the main information in image and ignore some irrelevant information, an EVAM attention model is designed under the framework of YOLOv5s detection network, which improves the saliency of pedestrian targets and suppress the background interference. The experimental results show that compared with nine typical algorithms, the proposed algorithm can achieve accurate detection of multi-scale targets in complex environments, and is significantly superior to the compared detection algorithms in both subjective and objective evaluation indicators. The mAP and recall rates of the proposed network can reach 88.9% and 87.5%, respectively.

27 November 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
Shuai HaoShuai Hao
Shuai Hao
JLJiahao Li
Jiahao Li
XMXu Ma
Xu Ma
SSSiya Sun
Siya Sun
ZTZhuo Tian
Zhuo Tian
YHYifeng Hou
Yifeng Hou
The number of samples is one of the key factors affecting the performance of deep learning-based detection networks. Aiming at the problem that the detection network is difficult to accurately detect the hot-spot fault targets under the condition of small samples, a photovoltaic hot-spot fault detection network based on progressive transfer learning and multi-scale feature fusion is proposed. First, a large number of artificial hot-spot samples are generated through the artificial model, and the mixed dataset containing real and artificial samples is constructed to improve the data diversity. On this basis, a pre-trained model based on artificial samples is established to learn the shallow features of hot-spot faults. Then, to fuse the multi-scale features and improve feature aggregation ability of detection network, a novel feature pyramid structure based on reparameterized generalized and multi-scale feature fusion (RepG-MSFF) is designed. Moreover, to balance the detection accuracy and speed, the spatial and channel reconstruction convolution is utilized to replace conventional convolution in the backbone network. Finally, to further accurately locate hot-spot targets, an adaptive threshold focal loss function is introduced. The experimental results indicate that in three different scenarios datasets, the detection accuracy can reach 87.9%, 88.6% and 87.7%, respectively, which is higher than that of other nine detection algorithms.

28 March 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Shuai HaoShuai Hao
Shuai Hao
TQTianrui Qi
Tianrui Qi
XMXu Ma
Xu Ma
JLJiahao Li
Jiahao Li
TLTianqi Li
Tianqi Li
In the process of utilizing thermal infrared sensors to identify photovoltaic (PV) hot-spot faults, due to the diverse shapes of hot-spot faults and environmental interferences, fault characteristics cannot be effectively expressed, which poses a challenge for traditional detection networks in achieving accurate detection. Consequently, an adaptive PV hot-spot fault detection network based on region perception and cross-channel feature aggregation is proposed. First, to reduce the interference of pseudo-highlight features in complex backgrounds, a Lite-UNet segmentation network is designed to remove background redundant information and enable the detection network to concentrate on the region of the PV panel. Second, to fully capture the geometric deformations and weak edge characteristics of hot-spot faults, a C2f DCN module is designed, which enhances the feature extraction capabilities by adaptively adjusting the receptive field. Subsequently, to address the problem of feature coupling often encountered in extracting dense hot-spot fault features, a dense object visual enhancement (DOVE) module was proposed. Through the dynamic aggregation of cross-space features, the feature information of different channels is integrated to improve the detection accuracy of hot-spot faults. Additionally, to further enhance the effective fusion of multi-scale features, an adaptive scale converter module (ASCM) detection head is designed. Finally, seven traditional detection methods are chosen for comparison in order to confirm the benefits of the proposed method. According to the experimental results, the suggested method can detect hot-spot faults with an accuracy of up to 86.5% in complicated inspection environments, which is an increase of 5.6% compared with the basis of original network.

5 June 2025 in Measurement Science and Technology
Verified
Journal Article
Closed access
Shuai HaoShuai Hao
Shuai Hao
TQTianrui Qi
Tianrui Qi
XMXu Ma
Xu Ma
ZTZhuo Tian
Zhuo Tian
JLJiahao Li
Jiahao Li
SFShiao Fan
Shiao Fan
In coal mine belt conveying systems, foreign objects falling may cause safety risks, such as conveyor belt tearing or blockage. To address these challenges in complex underground environments, a foreign object detection method for coal conveyor belts based on brightness self-balancing and multi-scale feature fusion called BS-MFFNet is introduced. First, to mitigate the impact of poor lighting and coal dust interference, an environmental perception dynamic enhancer is designed, thus improving image quality. Second, to enhance the detection accuracy of irregular targets, deformable convolutions are integrated into the backbone network. Subsequently, to further enhance feature representation capabilities, a multi-scale feature fusion network is developed, integrating both global and local information to provide richer target features. Lastly, an adaptive kernel-aware attention module is incorporated into the detection head to enhance target representation in complex, low-illumination backgrounds. Experimental results show that BS-MFFNet outperforms eight classical algorithms, achieving an average accuracy of 97.4%, an F 1 score of 0.93, and a detection speed of 74.6 fps in environments with weak lighting and high coal dust concentrations.

11 June 2026 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
Shuai HaoShuai Hao
Shuai Hao
TQTianrui Qi
Tianrui Qi
JLJiahao Li
Jiahao Li
XMXu Ma
Xu Ma
SSSiya Sun
Siya Sun
In the use of thermal infrared images for photovoltaic (PV) hot-spot fault detection, due to the low pixel percentage of hot-spot fault and interference of complex background, the fault characteristics cannot be effectively expressed, resulting in the decrease of detection accuracy of traditional algorithms. Therefore, a hot-spot fault detection network based on image segmentation and multi-scale feature fusion is proposed, abbreviated as IS-MSFFNet. First, to mitigate interference from pseudo-highlight regions, a PV panel image segmentation network is designed to remove the redundant background information. Second, based on the feature extraction of CSPDarkNet backbone network, an explicit visual center module is introduced to capture the hot-spot fault features in local corner regions. Then, to solve the problem of multi-scale features insufficient expression ability and difficulty in effective fusion, a MSAFF-BiFPN neck network is designed to improve detection accuracy of multi-scale hot-spot targets. Meanwhile, a detection layer of small hot-spot fault targets is added, which fully utilizes the shallow information and increases the multi-scale receptive field of detection model. Finally, the IS-MSFFNet is tested and verified on dataset provided by PV power station. The experimental results indicate that the proposed algorithm can accurately detect the PV hot-spot fault under complex background environment. In two different scenarios of rooftop and mountains, the detection accuracy can reach 85.6% and 86.3% respectively, which is an improvement of 5.4% and 4.8% on the basis of original network.